English
Related papers

Related papers: On the Prior Sensitivity of Thompson Sampling

200 papers

We study a widely used Bayesian optimization method, Gaussian process Thompson sampling (GP-TS), under the assumption that the objective function is a sample path from a GP. Compared with the GP upper confidence bound (GP-UCB) with…

Machine Learning · Statistics 2026-03-11 Shion Takeno , Shogo Iwazaki

This paper studies the one-shot behavior of no-regret algorithms for stochastic bandits. Although many algorithms are known to be asymptotically optimal with respect to the expected regret, over a single run, their pseudo-regret seems to…

Machine Learning · Computer Science 2023-12-01 Victor Boone

Reinforcement learning is an attractive approach to learn good resource allocation and scheduling policies based on data when the system model is unknown. However, the cumulative regret of most RL algorithms scales as $\tilde O(\mathsf{S}…

Machine Learning · Computer Science 2023-04-28 Nima Akbarzadeh , Aditya Mahajan

We improve the efficiency of algorithms for stochastic \emph{combinatorial semi-bandits}. In most interesting problems, state-of-the-art algorithms take advantage of structural properties of rewards, such as \emph{independence}. However,…

Machine Learning · Statistics 2019-06-24 Pierre Perrault , Vianney Perchet , Michal Valko

In model-based solution approaches to the problem of learning in an unknown environment, exploring to learn the model parameters takes a toll on the regret. The optimal performance with respect to regret or PAC bounds is achievable, if the…

Machine Learning · Computer Science 2015-10-13 P. Prasanna , Sarath Chandar , Balaraman Ravindran

We develop a model selection approach to tackle reinforcement learning with adversarial corruption in both transition and reward. For finite-horizon tabular MDPs, without prior knowledge on the total amount of corruption, our algorithm…

Machine Learning · Computer Science 2024-12-31 Chen-Yu Wei , Christoph Dann , Julian Zimmert

Mean rewards of actions are often correlated. The form of these correlations may be complex and unknown a priori, such as the preferences of a user for recommended products and their categories. To maximize statistical efficiency, it is…

Machine Learning · Computer Science 2022-02-04 Joey Hong , Branislav Kveton , Sumeet Katariya , Manzil Zaheer , Mohammad Ghavamzadeh

We study the benefits of sparsity in nonparametric contextual bandit problems, in which the set of candidate features is countably or uncountably infinite. Our contribution is two-fold. First, using a novel reduction to sequences of…

Machine Learning · Statistics 2026-01-16 Hamish Flynn , Julia Olkhovskaya , Paul Rognon-Vael

We consider the model selection task in the stochastic contextual bandit setting. Suppose we are given a collection of base contextual bandit algorithms. We provide a master algorithm that combines them and achieves the same performance, up…

Machine Learning · Computer Science 2020-06-09 Aurélien F. Bibaut , Antoine Chambaz , Mark J. van der Laan

Stochastic linear bandits are a fundamental model for sequential decision making, where an agent selects a vector-valued action and receives a noisy reward with expected value given by an unknown linear function. Although well studied in…

Machine Learning · Computer Science 2025-06-23 Bruce Huang , Ruida Zhou , Lin F. Yang , Suhas Diggavi

We study high-dimensional multi-armed contextual bandits with batched feedback where the $T$ steps of online interactions are divided into $L$ batches. In specific, each batch collects data according to a policy that depends on previous…

Machine Learning · Statistics 2023-11-27 Jianqing Fan , Zhaoran Wang , Zhuoran Yang , Chenlu Ye

We develop a form Thompson sampling for online learning under full feedback - also known as prediction with expert advice - where the learner's prior is defined over the space of an adversary's future actions, rather than the space of…

Machine Learning · Computer Science 2025-09-23 Alexander Terenin , Jeffrey Negrea

The question of the optimality of Thompson Sampling for solving the stochastic multi-armed bandit problem had been open since 1933. In this paper we answer it positively for the case of Bernoulli rewards by providing the first finite-time…

Machine Learning · Statistics 2012-07-20 Emilie Kaufmann , Nathaniel Korda , Rémi Munos

Algorithms for hyperparameter optimization abound, all of which work well under different and often unverifiable assumptions. Motivated by the general challenge of sequentially choosing which algorithm to use, we study the more specific…

Machine Learning · Statistics 2016-04-12 Robert Nishihara , David Lopez-Paz , Léon Bottou

We analyze the regret of combinatorial Thompson sampling (CTS) for the combinatorial multi-armed bandit with probabilistically triggered arms under the semi-bandit feedback setting. We assume that the learner has access to an exact…

Machine Learning · Computer Science 2019-02-20 Alihan Hüyük , Cem Tekin

We present improved algorithms with worst-case regret guarantees for the stochastic linear bandit problem. The widely used "optimism in the face of uncertainty" principle reduces a stochastic bandit problem to the construction of a…

Machine Learning · Statistics 2024-09-06 Hamish Flynn , David Reeb , Melih Kandemir , Jan Peters

Simple regret is a natural and parameter-free performance criterion for pure exploration in multi-armed bandits yet is less popular than the probability of missing the best arm or an $\epsilon$-good arm, perhaps due to lack of easy ways to…

Machine Learning · Computer Science 2023-02-03 Yao Zhao , Connor James Stephens , Csaba Szepesvári , Kwang-Sung Jun

Stochastic Rank-One Bandits (Katarya et al, (2017a,b)) are a simple framework for regret minimization problems over rank-one matrices of arms. The initially proposed algorithms are proved to have logarithmic regret, but do not match the…

Machine Learning · Statistics 2019-12-09 Cindy Trinh , Emilie Kaufmann , Claire Vernade , Richard Combes

We consider settings where an allocation has to be chosen repeatedly, returns are unknown but can be learned, and decisions are subject to constraints. Our model covers two-sided and one-sided matching, even with complex constraints. We…

Econometrics · Economics 2020-11-05 Maximilian Kasy , Alexander Teytelboym

We consider reinforcement learning in parameterized Markov Decision Processes (MDPs), where the parameterization may induce correlation across transition probabilities or rewards. Consequently, observing a particular state transition might…

Machine Learning · Statistics 2015-04-01 Aditya Gopalan , Shie Mannor